Quantization publisher
Ex0bit
Ex0bit publishes 3 quantizations across 1 models in our index, averaging 3.712 effective bits per weight. Their files differ in size from other publishers' builds of the same nominal quantization on 3 of the pairs we can compare — the same label does not mean the same file.
From the file· summed file bytes
Repositories
1
Quantizations
3
Models covered
1
Avg effective bpw
3.712
across their files
Same model, same quant label, different bytes
largest disagreements first
| Model | Quant | Ex0bit | vs | Theirs | Difference |
|---|---|---|---|---|---|
| step-3.5-flash | Q3_K_L | 95.03 GiB | bartowski | 87.26 GiB | +8.9% |
| step-3.5-flash | IQ2_M | 59.59 GiB | bartowski | 58.63 GiB | +1.6% |
| step-3.5-flash | IQ4_NL | 103.86 GiB | bartowski | 103.97 GiB | -0.1% |
A quantization label describes a target, not a recipe. Publishers make different choices about which tensors to keep at higher precision, and some apply an importance matrix while others don't — so two files both honestly labelled the same thing can differ measurably in size and in quality.
Models they publish
| Model | Quantizations | Smallest |
|---|---|---|
| step-3.5-flash | 3 | 59.59 GiB |